Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    describing attributes and connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.42
    0.35
    వ్వ
    0.34
    a
    0.33
     infographics
    0.33
    是一个
    0.32
    视野
    0.32
     એક
    0.32
     ها
    0.31
     The
    0.31
    POSITIVE LOGITS
     requiring
    0.55
     containing
    0.54
     resembling
    0.51
     consisting
    0.47
     utilizing
    0.46
     featuring
    0.45
     которой
    0.45
     depicting
    0.45
     comprising
    0.44
     embodying
    0.44
    Act Density 0.166%

    No Known Activations